1 Load environment

Code

import warnings

warnings.filterwarnings("ignore")

import matplotlib.pyplot as plt
import seaborn as sns
import scanpy as sc
import pandas as pd
import numpy as np
import random
import itertools

from tqdm import tqdm

import decoupler as dc
import sys

sys.path.append("./../../../../utilities_folder")
from utilities import load_object, intTable, plotGenesInTerm, getAnnGenes, run_ora_catchErrors

Set R environment with rpy2:

Code

import rpy2.rinterface_lib.callbacks
import anndata2ri
import logging

from rpy2.robjects import pandas2ri
import rpy2.robjects as ro

sc.settings.verbosity = 0
rpy2.rinterface_lib.callbacks.logger.setLevel(logging.ERROR)

pandas2ri.activate()
anndata2ri.activate()

%load_ext rpy2.ipython

Set up of graphical parameters for Python plots:

Code

%matplotlib inline
sc.set_figure_params(dpi = 300, fontsize = 20)

cmap_up = sns.light_palette("red", as_cmap=True)
cmap_down = sns.light_palette("blue", as_cmap=True)
cmap_all = sns.light_palette("seagreen", as_cmap=True)

Set up of graphical parameters for R plots:

Code

default_units = 'in' 
default_res = 300
default_width = 10
default_height = 9

import rpy2
old_setup_graphics = rpy2.ipython.rmagic.RMagics.setup_graphics

def new_setup_graphics(self, args):
    if getattr(args, 'units') is not None:
        if args.units != default_units:
            return old_setup_graphics(self, args)
    args.units = default_units
    if getattr(args, 'res') is None:
        args.res = default_res
    if getattr(args, 'width') is None:
        args.width = default_width
    if getattr(args, 'height') is None:
        args.height = default_height        
    return old_setup_graphics(self, args)


rpy2.ipython.rmagic.RMagics.setup_graphics = new_setup_graphics

Here the cell were we inject the parameters using Quarto renderer:

Code

# Injected Parameters
N = 3

Code

# Injected Parameters
N = 12

Import R libraries:

Code

%%R
source('./../../../../utilities_folder/GO_helper.r')
loc <- './../../../../R_loc' # pointing to the renv environment

.libPaths(loc)

library('topGO')
library('org.Hs.eg.db')
library(dplyr)
library(ggplot2)

Set output folders:

Code

output_folder = './'
folder = './deg_in_cluster_tables/cluster_' + str(N) + '/'

import os

if not os.path.isdir(folder):
    os.makedirs(folder)

2 Load data

Here we load the anndata:

Code

GO2gene = load_object('./../../../../data/GO2gene_complete.pickle')

Here we load the dictionary that associates to each GO term its genes:

Code

adata = sc.read("1_All_Annotated_Triku.h5ad")
adata

AnnData object with n_obs × n_vars = 27925 × 14582
    obs: 'sample_id', 'run_id', 'probe_barcode_ids', 'subject', 'line', 'specimen', 'stage', 'condition', 'notes', 'seqRun', 'original_name', 'project', 'who', 'SC_derivation', 'micoplasma', 'mosaic', 'genSite', 'n_genes_by_counts', 'log1p_n_genes_by_counts', 'total_counts', 'log1p_total_counts', 'total_counts_mito', 'log1p_total_counts_mito', 'pct_counts_mito', 'total_counts_ribo', 'log1p_total_counts_ribo', 'pct_counts_ribo', 'gene_UMI_ratio', 'log1p_gene_UMI_ratio', 'scDblFinder_score', 'scDblFinder_class', 'n_counts', 'n_genes', 'leiden', 'score_pluripotency', 'score_mesoderm', 'score_PS', 'score_EM', 'score_AM', 'score_Endo', 'score_Epi', 'score_HEP', 'score_NM', 'score_ExM', 'score_Ery', 'score_EAE', 'score_Amnion_LC', 'score_AxM', 'score_Amnion', 'score_NNE', 'score_PGC', 'score_hPGCLCs', 'score_DE1', 'score_DE2', 'score_Hypoblast', 'score_YS', 'score_EMPs', 'score_Endothelium', 'score_Myeloid_Progenitors', 'score_Megakaryocyte_Erythroid_progenitors', 'CellTypes'
    var: 'n_cells', 'mito', 'ribo', 'n_cells_by_counts', 'mean_counts', 'log1p_mean_counts', 'pct_dropout_by_counts', 'total_counts', 'log1p_total_counts', 'highly_variable', 'means', 'dispersions', 'dispersions_norm', 'highly_variable_nbatches', 'highly_variable_intersection', 'triku_distance', 'triku_distance_uncorrected', 'triku_highly_variable'
    uns: 'CellTypes_colors', 'dendrogram_CellTypes', 'dendrogram_leiden', 'dendrogram_specimen', 'hvg', 'leiden', 'leiden_colors', 'log1p', 'neighbors', 'pca', 'rank_genes_groups', 'run_id_colors', 'sample_id_colors', 'specimen_colors', 'stage_colors', 'triku_params', 'umap'
    obsm: 'X_pca', 'X_pca_harmony', 'X_umap'
    varm: 'PCs'
    layers: 'raw'
    obsp: 'connectivities', 'distances'

3 Markers of cluster

We filter genes for the cluster under investigation based on the p-value adjusted that we then convert in -log(p-value adjusted):

Code

markers = sc.get.rank_genes_groups_df(adata, group=str(N))
intTable(markers, folder=folder, fileName = 'markers_cluster_before_filtering_' + str(N) + '.xlsx', save = True)

Code

markers = markers.set_index('names')
markers = markers[markers.pvals_adj < 0.01]
markers['FDR'] = markers['pvals_adj']
markers['-log10(FDR)'] = -np.log10(markers.pvals_adj)
markers = markers.replace(np.inf, markers[markers['-log10(FDR)'] != np.inf]['-log10(FDR)'].max())
markers

	scores	logfoldchanges	pvals	pvals_adj	pct_nz_group	pct_nz_reference	FDR	-log10(FDR)
names
PLVAP	12.707981	11.120005	5.339515e-37	2.777900e-33	1.000000	0.014459	2.777900e-33	32.556283
PRCP	12.698975	4.174765	5.990920e-37	2.777900e-33	1.000000	0.815830	2.777900e-33	32.556283
EGFL7	12.688288	4.863193	6.867082e-37	2.777900e-33	1.000000	0.651215	2.777900e-33	32.556283
IGFBP4	12.680135	4.255943	7.620081e-37	2.777900e-33	1.000000	0.719170	2.777900e-33	32.556283
LMO2	12.662561	7.592786	9.533681e-37	2.780403e-33	1.000000	0.063830	2.780403e-33	32.555892
...	...	...	...	...	...	...	...	...
CDH3	-10.509672	-6.141855	7.796404e-26	1.249310e-23	0.074074	0.846292	1.249310e-23	22.903330
PDPN	-10.981018	-4.760371	4.715802e-28	1.026356e-25	0.222222	0.922213	1.026356e-25	24.988702
DSG2	-11.407045	-4.130790	3.856060e-30	1.102531e-27	0.388889	0.975458	1.102531e-27	26.957609
TPM1	-11.499954	-2.862785	1.319854e-30	4.475840e-28	0.851852	0.997166	4.475840e-28	27.349125
APOE	-12.172976	-5.003693	4.330044e-34	3.323195e-31	0.444444	0.986438	3.323195e-31	30.478444

3194 rows × 8 columns

Code

intTable(markers, folder=folder, fileName = 'markers_cluster_filtered_' + str(N) + '.xlsx', save = True)

3.1 Select up and downregulated markers

3.1.1 Up

Code

pos = markers[markers.logfoldchanges > 1]
pos

	scores	logfoldchanges	pvals	pvals_adj	pct_nz_group	pct_nz_reference	FDR	-log10(FDR)
names
PLVAP	12.707981	11.120005	5.339515e-37	2.777900e-33	1.000000	0.014459	2.777900e-33	32.556283
PRCP	12.698975	4.174765	5.990920e-37	2.777900e-33	1.000000	0.815830	2.777900e-33	32.556283
EGFL7	12.688288	4.863193	6.867082e-37	2.777900e-33	1.000000	0.651215	2.777900e-33	32.556283
IGFBP4	12.680135	4.255943	7.620081e-37	2.777900e-33	1.000000	0.719170	2.777900e-33	32.556283
LMO2	12.662561	7.592786	9.533681e-37	2.780403e-33	1.000000	0.063830	2.780403e-33	32.555892
...	...	...	...	...	...	...	...	...
BAHCC1	3.093874	1.382778	1.975613e-03	9.168808e-03	0.481481	0.237343	9.168808e-03	2.037687
PCDHB13	3.079731	2.111494	2.071875e-03	9.554739e-03	0.351852	0.125543	9.554739e-03	2.019781
KANK2	3.073952	1.043641	2.112432e-03	9.701884e-03	0.574074	0.400273	9.701884e-03	2.013144
CLCF1	3.070328	2.877944	2.138239e-03	9.801886e-03	0.296296	0.063722	9.801886e-03	2.008690
YAF2	3.067582	1.401985	2.157982e-03	9.870668e-03	0.462963	0.230634	9.870668e-03	2.005653

1035 rows × 8 columns

Code

pos['-log10(FDR)'] = -np.log10(pos.pvals_adj)
#pos = pos.fillna('inf')
pos = pos.replace(np.inf, pos[pos['-log10(FDR)'] != np.inf]['-log10(FDR)'].max())
pos['FDR'] = pos['pvals_adj']
up_regGenes = pos.index.tolist()
allUpSelected = adata.var_names.isin(up_regGenes).astype('int').tolist()

3.1.2 Down

Code

neg = markers[markers.logfoldchanges < -1].sort_values(by = 'logfoldchanges')
neg

	scores	logfoldchanges	pvals	pvals_adj	pct_nz_group	pct_nz_reference	FDR	-log10(FDR)
names
CRABP1	-8.896342	-32.536915	5.771747e-19	3.914587e-17	0.000000	0.699652	3.914587e-17	16.407314
CDH1	-9.270901	-32.328884	1.845801e-20	1.529288e-18	0.000000	0.729109	1.529288e-18	17.815511
APELA	-7.923219	-31.872980	2.314391e-15	1.010433e-13	0.000000	0.623121	1.010433e-13	12.995493
ZIC5	-7.752136	-31.591059	9.035978e-15	3.680520e-13	0.000000	0.609666	3.680520e-13	12.434091
LRAT	-6.549989	-30.975891	5.754135e-11	1.292863e-09	0.000000	0.515123	1.292863e-09	8.888448
...	...	...	...	...	...	...	...	...
LGMN	-3.666079	-1.004122	2.462982e-04	1.487788e-03	0.592593	0.819239	1.487788e-03	2.827459
SKIL	-4.903836	-1.003762	9.398290e-07	1.012904e-05	0.796296	0.912561	1.012904e-05	4.994432
PKD2	-3.359252	-1.003080	7.815376e-04	4.105324e-03	0.500000	0.720247	4.105324e-03	2.386653
MTREX	-3.623219	-1.002154	2.909592e-04	1.727511e-03	0.537037	0.738258	1.727511e-03	2.762579
EIF3M	-5.658023	-1.000727	1.531267e-08	2.293966e-07	0.851852	0.937354	2.293966e-07	6.639413

1399 rows × 8 columns

Code

neg['-log10(FDR)'] = -np.log10(neg.pvals_adj)
#neg = neg.fillna('inf')
neg = neg.replace(np.inf, neg[neg['-log10(FDR)'] != np.inf]['-log10(FDR)'].max())
neg['FDR'] = neg['pvals_adj']
down_regGenes = neg.index.tolist()
allDownSelected = adata.var_names.isin(down_regGenes).astype('int').tolist()

3.1.3 All regulated

Code

all_sign = up_regGenes + down_regGenes
allSelected = adata.var_names.isin(all_sign).astype('int').tolist()
allGenes = adata.var_names.tolist()

4 topGO

4.1 Upregulated

Code

%%R -i allUpSelected -i allGenes

allGenes_v <- c(allUpSelected)
#print(allGenes_v)
names(allGenes_v) <- allGenes
allGenes_v <- unlist(allGenes_v)

geneNames <- c(allGenes)

ann_org_BP <- topGO::annFUN.org(whichOnto='BP', feasibleGenes=names(allGenes_v), 
                           mapping='org.Hs.eg', ID='symbol')

ann_org_MF <- topGO::annFUN.org(whichOnto='MF', feasibleGenes=names(allGenes_v), 
                           mapping='org.Hs.eg', ID='symbol')

ann_org_CC <- topGO::annFUN.org(whichOnto='CC', feasibleGenes=names(allGenes_v), 
                           mapping='org.Hs.eg', ID='symbol')

selection <- function(allScores){return (as.logical(allScores))}

Biological Process

Get topGO results:

Code

%%R -o results

GOdata <- new("topGOdata",
  ontology="BP",
  allGenes=allGenes_v,
  annot=annFUN.GO2genes,
  GO2genes=ann_org_BP,
  geneSel = selection,
  nodeSize=10)

results <- runTest(GOdata, algorithm="weight01",statistic="fisher")

Convert results from R environment to Python:

Code

scores = ro.r.score(results)
score_names = ro.r(
'''
names(results@score)
'''
)
go_data = ro.r.GOdata

genesData = ro.r(
'''
geneData(results)
'''
)
genesData

array([13071,   952,    10,  5409], dtype=int32)

Code

#num_summarize = min(100, len(score_names))
results_table = ro.r.GenTable(go_data, weight=results,
        orderBy="weight", topNodes=len(scores))

results_table_py = ro.conversion.rpy2py(results_table)

scores_py = ro.conversion.rpy2py(scores)
score_names = [i for i in score_names]

scores_df = pd.DataFrame({'Scores': scores_py, 'GO.ID': score_names})
results_table_py = results_table_py.merge(scores_df, left_on = 'GO.ID', right_on = 'GO.ID')
results_table_py

	GO.ID	Term	Annotated	Significant	Expected	weight	Scores
0	GO:0001570	vasculogenesis	74	29	5.39	5.4e-12	5.427433e-12
1	GO:0001525	angiogenesis	450	123	32.77	1.2e-11	1.180013e-11
2	GO:0003180	aortic valve morphogenesis	29	16	2.11	1.5e-11	1.527048e-11
3	GO:0016525	negative regulation of angiogenesis	81	25	5.90	5.1e-11	5.130094e-11
4	GO:0030335	positive regulation of cell migration	447	98	32.56	7.3e-11	7.339487e-11
...	...	...	...	...	...	...	...
6269	GO:2000757	negative regulation of peptidyl-lysine a...	20	0	1.46	1.00000	1.000000e+00
6270	GO:2000767	positive regulation of cytoplasmic trans...	13	0	0.95	1.00000	1.000000e+00
6271	GO:2001034	positive regulation of double-strand bre...	15	0	1.09	1.00000	1.000000e+00
6272	GO:2001169	regulation of ATP biosynthetic process	16	0	1.17	1.00000	1.000000e+00
6273	GO:2001244	positive regulation of intrinsic apoptot...	45	0	3.28	1.00000	1.000000e+00

6274 rows × 7 columns

Filter results:

Code

results_table_py = results_table_py[results_table_py['Scores'] < 0.05]
results_table_py = results_table_py[results_table_py['Annotated'] < 200]
results_table_py = results_table_py[results_table_py['Annotated'] > 15]

results_table_py['-log10(pvalue)'] = - np.log10(results_table_py.Scores)
results_table_py['Significant/Annotated'] = results_table_py['Significant'] / results_table_py['Annotated']

Code

intTable(results_table_py, folder = folder, fileName = 'GO_BP_up.xlsx', save = True)

Code

%%R
Res <- GenTable(GOdata, weight=results,
        orderBy="weight", topNodes=length(score(results)))
#print(Res[0:10,])
colnames(Res) <- c("GO.ID", "Term", "Annotated", "Significant", "Expected", "Statistics")
Res$ER <- Res$Significant / Res$Expected
bubbleplot(Res, Ont = 'BP', fillCol = 'red')

Code

%%R -i markers
plotGenesInTerm_v1(Res, GOdata, SE = markers, nterms=15, ngenes=12,
                             fillCol='red', log = TRUE)

Code

%%R -i markers -i folder
saveGenesInTerm(Res, GOdata, nterms = 20, path = paste0(folder,'GO_BP_genesInTerm_up.xlsx'), SE = markers)

Molecular Function

Code

%%R

GOdata <- new("topGOdata",
  ontology="MF",
  allGenes=allGenes_v,
  annot=annFUN.GO2genes,
  GO2genes=ann_org_MF,
  geneSel = selection,
  nodeSize=10)

Code

%%R -o results

results <- runTest(GOdata, algorithm="weight01",statistic="fisher")

Code

scores = ro.r.score(results)
score_names = ro.r(
'''
names(results@score)
'''
)
go_data = ro.r.GOdata

genesData = ro.r(
'''
geneData(results)
'''
)
genesData

array([13424,   971,    10,   871], dtype=int32)

Code

#num_summarize = min(100, len(score_names))
results_table = ro.r.GenTable(go_data, weight=results,
        orderBy="weight", topNodes=len(scores))

Code

results_table_py = ro.conversion.rpy2py(results_table)

Code

scores_py = ro.conversion.rpy2py(scores)
score_names = [i for i in score_names]

Code

scores_df = pd.DataFrame({'Scores': scores_py, 'GO.ID': score_names})
results_table_py = results_table_py.merge(scores_df, left_on = 'GO.ID', right_on = 'GO.ID')
results_table_py = results_table_py[results_table_py['Scores'] < 0.05]
results_table_py = results_table_py[results_table_py['Annotated'] < 200]
results_table_py = results_table_py[results_table_py['Annotated'] > 15]

intTable(results_table_py, folder = folder, fileName = 'GO_MF_up.xlsx', save = True)

Code

%%R
Res <- GenTable(GOdata, weight=results,
        orderBy="weight", topNodes=length(score(results)))
#print(Res[0:10,])
colnames(Res) <- c("GO.ID", "Term", "Annotated", "Significant", "Expected", "Statistics")
Res$ER <- Res$Significant / Res$Expected
bubbleplot(Res, Ont = 'MF', fillCol = 'red')

Code

%%R -i markers
plotGenesInTerm_v1(Res, GOdata, SE = markers, nterms=15, ngenes=12,
                             fillCol='red', log = TRUE)

Code

%%R -i markers -i folder
saveGenesInTerm(Res, GOdata, nterms = 20, path = paste0(folder,'GO_MF_genesInTerm_up.xlsx'), SE = markers)

Cellular Compartment

Code

%%R

GOdata <- new("topGOdata",
  ontology="CC",
  allGenes=allGenes_v,
  annot=annFUN.GO2genes,
  GO2genes=ann_org_CC,
  geneSel = selection,
  nodeSize=10)

Code

%%R -o results

results <- runTest(GOdata, algorithm="weight01",statistic="fisher")

Code

scores = ro.r.score(results)
score_names = ro.r(
'''
names(results@score)
'''
)
go_data = ro.r.GOdata

genesData = ro.r(
'''
geneData(results)
'''
)
genesData

array([13666,   990,    10,   590], dtype=int32)

Code

#num_summarize = min(100, len(score_names))
results_table = ro.r.GenTable(go_data, weight=results,
        orderBy="weight", topNodes=len(scores))

Code

results_table_py = ro.conversion.rpy2py(results_table)

Code

scores_py = ro.conversion.rpy2py(scores)
score_names = [i for i in score_names]

Code

scores_df = pd.DataFrame({'Scores': scores_py, 'GO.ID': score_names})
results_table_py = results_table_py.merge(scores_df, left_on = 'GO.ID', right_on = 'GO.ID')

Code

results_table_py = results_table_py[results_table_py['Scores'] < 0.05]
results_table_py = results_table_py[results_table_py['Annotated'] < 200]
results_table_py = results_table_py[results_table_py['Annotated'] > 15]

intTable(results_table_py, folder = folder, fileName = 'GO_CC_up.xlsx', save = True)

Code

%%R
Res <- GenTable(GOdata, weight=results,
        orderBy="weight", topNodes=length(score(results)))
#print(Res[0:10,])
colnames(Res) <- c("GO.ID", "Term", "Annotated", "Significant", "Expected", "Statistics")
Res$ER <- Res$Significant / Res$Expected
bubbleplot(Res, Ont = 'CC', fillCol = 'red')

Code

%%R -i markers
plotGenesInTerm_v1(Res, GOdata, SE = markers, nterms=12, ngenes=12,
                             fillCol='red', log = TRUE)

Code

%%R -i markers -i folder
saveGenesInTerm(Res, GOdata, nterms = 20, path = paste0(folder,'GO_CC_genesInTerm_up.xlsx'), SE = markers)

Pathway annotation

4.1.0.1 Reactome

Code

curated = msigdb[msigdb['collection'].isin(['reactome_pathways'])]
curated = curated[~curated.duplicated(['geneset', 'genesymbol'])]

aggregated = curated[["geneset", "genesymbol"]].groupby("geneset").count().rename(columns={"genesymbol": "gene_count"})
curated = curated[~curated.geneset.isin(aggregated[aggregated.gene_count > 200].index.tolist())].copy()
curated = curated[~curated.geneset.isin(aggregated[aggregated.gene_count < 15].index.tolist())].copy()

Code

rank = pd.DataFrame(markers['-log10(FDR)'])

rank_copy = rank.copy()
rank_copy['pval'] = markers.loc[rank.index].FDR

Code

rank_copy

	-log10(FDR)	pval
names
PLVAP	32.556283	2.777900e-33
PRCP	32.556283	2.777900e-33
EGFL7	32.556283	2.777900e-33
IGFBP4	32.556283	2.777900e-33
LMO2	32.555892	2.780403e-33
...	...	...
CDH3	22.903330	1.249310e-23
PDPN	24.988702	1.026356e-25
DSG2	26.957609	1.102531e-27
TPM1	27.349125	4.475840e-28
APOE	30.478444	3.323195e-31

3194 rows × 2 columns

Code

results_table_py = run_ora_catchErrors(mat=rank.T, net=curated, source='geneset', target='genesymbol', verbose=False, n_up=len(rank), n_bottom=0)
len(results_table_py)

766

Code

intTable(results_table_py, folder = folder, fileName = 'Reactome_up.xlsx', save = True)

Code

if len(results_table_py) > 0:
    results_table_py = getAnnGenes(results_table_py, GO2gene['reactome_pathways'], rank_copy)
    _, df = plotGenesInTerm(results = results_table_py, 
                            GO2gene = GO2gene['reactome_pathways'], DEGs = rank_copy, n_top_terms = 10, cmap = cmap_up)

Code

if len(results_table_py) > 0:
    intTable(df, folder = folder, fileName = 'genesInTerm_Reactome_up.xlsx', save = True)

4.1.0.2 KEGG

Code

curated = msigdb[msigdb['collection'].isin(['kegg_pathways'])]
curated = curated[~curated.duplicated(['geneset', 'genesymbol'])]

aggregated = curated[["geneset", "genesymbol"]].groupby("geneset").count().rename(columns={"genesymbol": "gene_count"})
curated = curated[~curated.geneset.isin(aggregated[aggregated.gene_count > 200].index.tolist())].copy()
curated = curated[~curated.geneset.isin(aggregated[aggregated.gene_count < 15].index.tolist())].copy()
results_table_py = run_ora_catchErrors(mat=rank.T, net=curated, source='geneset', target='genesymbol', verbose=False, n_up=len(rank), n_bottom=0)

Code

intTable(results_table_py, folder = folder, fileName = 'KEGG_up.xlsx', save = True)

Code

if len(results_table_py) > 0:
    results_table_py = getAnnGenes(results_table_py, GO2gene['kegg_pathways'], rank_copy)
    _, df = plotGenesInTerm(results_table_py, GO2gene['kegg_pathways'], rank_copy, n_top_terms = 10, n_top_genes = 15, cmap = cmap_up)

Code

if len(results_table_py) > 0:
    intTable(df, folder = folder, fileName = 'genesInTerm_KEGG_up.xlsx', save = True)

4.2 Downregulated

Code

%%R -i allDownSelected -i allGenes

allGenes_v <- c(allDownSelected)
#print(allGenes_v)
names(allGenes_v) <- allGenes
allGenes_v <- unlist(allGenes_v)

geneNames <- c(allGenes)

ann_org_BP <- topGO::annFUN.org(whichOnto='BP', feasibleGenes=names(allGenes_v), 
                           mapping='org.Hs.eg', ID='symbol')

ann_org_MF <- topGO::annFUN.org(whichOnto='MF', feasibleGenes=names(allGenes_v), 
                           mapping='org.Hs.eg', ID='symbol')

ann_org_CC <- topGO::annFUN.org(whichOnto='CC', feasibleGenes=names(allGenes_v), 
                           mapping='org.Hs.eg', ID='symbol')

selection <- function(allScores){return (as.logical(allScores))}

Biological Process

Code

%%R
#print(lapply(ann_org_BP, count_genes))

GOdata <- new("topGOdata",
  ontology="BP",
  allGenes=allGenes_v,
  annot=annFUN.GO2genes,
  GO2genes=ann_org_BP,
  geneSel = selection,
  nodeSize=10)

Code

%%R -o results

results <- runTest(GOdata, algorithm="weight01",statistic="fisher")

Code

scores = ro.r.score(results)
score_names = ro.r(
'''
names(results@score)
'''
)
go_data = ro.r.GOdata

genesData = ro.r(
'''
geneData(results)
'''
)
genesData

array([13071,  1303,    10,  5745], dtype=int32)

Code

#num_summarize = min(100, len(score_names))
results_table = ro.r.GenTable(go_data, weight=results,
        orderBy="weight", topNodes=len(scores))

Code

results_table_py = ro.conversion.rpy2py(results_table)

Code

scores_py = ro.conversion.rpy2py(scores)
score_names = [i for i in score_names]

Code

scores_df = pd.DataFrame({'Scores': scores_py, 'GO.ID': score_names})
results_table_py = results_table_py.merge(scores_df, left_on = 'GO.ID', right_on = 'GO.ID')
results_table_py

	GO.ID	Term	Annotated	Significant	Expected	weight	Scores
0	GO:0060670	branching involved in labyrinthine layer...	11	7	1.10	2.2e-05	0.000022
1	GO:0150104	transport across blood-brain barrier	78	20	7.78	5.6e-05	0.000056
2	GO:0072112	podocyte differentiation	20	9	1.99	0.00014	0.000142
3	GO:0009063	cellular amino acid catabolic process	86	18	8.57	0.00016	0.000155
4	GO:0009070	serine family amino acid biosynthetic pr...	14	7	1.40	0.00018	0.000176
...	...	...	...	...	...	...	...
6269	GO:2000767	positive regulation of cytoplasmic trans...	13	0	1.30	1.00000	1.000000
6270	GO:2000826	regulation of heart morphogenesis	10	0	1.00	1.00000	1.000000
6271	GO:2001223	negative regulation of neuron migration	10	0	1.00	1.00000	1.000000
6272	GO:2001241	positive regulation of extrinsic apoptot...	10	0	1.00	1.00000	1.000000
6273	GO:2001267	regulation of cysteine-type endopeptidas...	14	0	1.40	1.00000	1.000000

6274 rows × 7 columns

Code

results_table_py = results_table_py[results_table_py['Scores'] < 0.05]
results_table_py = results_table_py[results_table_py['Annotated'] < 200]
results_table_py = results_table_py[results_table_py['Annotated'] > 15]

Code

results_table_py['-log10(pvalue)'] = - np.log10(results_table_py.Scores)
results_table_py['Significant/Annotated'] = results_table_py['Significant'] / results_table_py['Annotated']

Code

intTable(results_table_py, folder = folder, fileName = 'GO_BP_down.xlsx', save = True)

Code

%%R
Res <- GenTable(GOdata, weight=results,
        orderBy="weight", topNodes=length(score(results)))
#print(Res[0:10,])
colnames(Res) <- c("GO.ID", "Term", "Annotated", "Significant", "Expected", "Statistics")
Res$ER <- Res$Significant / Res$Expected
bubbleplot(Res, Ont = 'BP', fillCol = 'blue')

Code

%%R -i markers
plotGenesInTerm_v1(Res, GOdata, SE = markers, nterms=15, ngenes=12,
                             fillCol='blue', log = TRUE)

Code

%%R -i markers -i folder
saveGenesInTerm(Res, GOdata, nterms = 20, path = paste0(folder,'GO_BP_genesInTerm_down.xlsx'), SE = markers)

Molecular Function

Code

%%R

GOdata <- new("topGOdata",
  ontology="MF",
  allGenes=allGenes_v,
  annot=annFUN.GO2genes,
  GO2genes=ann_org_MF,
  geneSel = selection,
  nodeSize=10)

Code

%%R -o results

results <- runTest(GOdata, algorithm="weight01",statistic="fisher")

Code

scores = ro.r.score(results)
score_names = ro.r(
'''
names(results@score)
'''
)
go_data = ro.r.GOdata

genesData = ro.r(
'''
geneData(results)
'''
)
genesData

array([13424,  1320,    10,  1046], dtype=int32)

Code

#num_summarize = min(100, len(score_names))
results_table = ro.r.GenTable(go_data, weight=results,
        orderBy="weight", topNodes=len(scores))

Code

results_table_py = ro.conversion.rpy2py(results_table)

Code

scores_py = ro.conversion.rpy2py(scores)
score_names = [i for i in score_names]

Code

scores_df = pd.DataFrame({'Scores': scores_py, 'GO.ID': score_names})
results_table_py = results_table_py.merge(scores_df, left_on = 'GO.ID', right_on = 'GO.ID')
results_table_py = results_table_py[results_table_py['Scores'] < 0.05]
results_table_py = results_table_py[results_table_py['Annotated'] < 200]
results_table_py = results_table_py[results_table_py['Annotated'] > 15]

intTable(results_table_py, folder = folder, fileName = 'GO_MF_down.xlsx', save = True)

Code

%%R
Res <- GenTable(GOdata, weight=results,
        orderBy="weight", topNodes=length(score(results)))
#print(Res[0:10,])
colnames(Res) <- c("GO.ID", "Term", "Annotated", "Significant", "Expected", "Statistics")
Res$ER <- Res$Significant / Res$Expected
bubbleplot(Res, Ont = 'MF', fillCol = 'blue')

Code

%%R -i markers
plotGenesInTerm_v1(Res, GOdata, SE = markers, nterms=15, ngenes=12,
                             fillCol='blue', log = TRUE)

Code

%%R -i markers -i folder
saveGenesInTerm(Res, GOdata, nterms = 20, path = paste0(folder,'GO_MF_genesInTerm_down.xlsx'), SE = markers)

Cellular Compartment

Code

%%R

GOdata <- new("topGOdata",
  ontology="CC",
  allGenes=allGenes_v,
  annot=annFUN.GO2genes,
  GO2genes=ann_org_CC,
  geneSel = selection,
  nodeSize=10)

Code

%%R -o results

results <- runTest(GOdata, algorithm="weight01",statistic="fisher")

Code

scores = ro.r.score(results)
score_names = ro.r(
'''
names(results@score)
'''
)
go_data = ro.r.GOdata

genesData = ro.r(
'''
geneData(results)
'''
)
genesData

array([13666,  1339,    10,   728], dtype=int32)

Code

#num_summarize = min(100, len(score_names))
results_table = ro.r.GenTable(go_data, weight=results,
        orderBy="weight", topNodes=len(scores))

Code

results_table_py = ro.conversion.rpy2py(results_table)

Code

scores_py = ro.conversion.rpy2py(scores)
score_names = [i for i in score_names]

Code

scores_df = pd.DataFrame({'Scores': scores_py, 'GO.ID': score_names})
results_table_py = results_table_py.merge(scores_df, left_on = 'GO.ID', right_on = 'GO.ID')

Code

results_table_py = results_table_py[results_table_py['Scores'] < 0.05]
results_table_py = results_table_py[results_table_py['Annotated'] < 200]
results_table_py = results_table_py[results_table_py['Annotated'] > 15]

intTable(results_table_py, folder = folder, fileName = 'GO_CC_down.xlsx', save = True)

Code

%%R
Res <- GenTable(GOdata, weight=results,
        orderBy="weight", topNodes=length(score(results)))
#print(Res[0:10,])
colnames(Res) <- c("GO.ID", "Term", "Annotated", "Significant", "Expected", "Statistics")
Res$ER <- Res$Significant / Res$Expected
bubbleplot(Res, Ont = 'CC', fillCol = 'blue')

Code

%%R -i markers
plotGenesInTerm_v1(Res, GOdata, SE = markers, nterms=12, ngenes=12,
                             fillCol='blue', log = TRUE)

Code

%%R -i markers -i folder
saveGenesInTerm(Res, GOdata, nterms = 20, path = paste0(folder,'GO_CC_genesInTerm_down.xlsx'), SE = markers)

Pathway annotation

4.2.0.1 Reactome

Code

curated = msigdb[msigdb['collection'].isin(['reactome_pathways'])]
curated = curated[~curated.duplicated(['geneset', 'genesymbol'])]

aggregated = curated[["geneset", "genesymbol"]].groupby("geneset").count().rename(columns={"genesymbol": "gene_count"})
curated = curated[~curated.geneset.isin(aggregated[aggregated.gene_count > 200].index.tolist())].copy()
curated = curated[~curated.geneset.isin(aggregated[aggregated.gene_count < 15].index.tolist())].copy()

Code

rank = pd.DataFrame(markers['-log10(FDR)'])

rank_copy = rank.copy()
rank_copy['pval'] = markers.loc[rank.index].FDR

Code

rank_copy

	-log10(FDR)	pval
names
PLVAP	32.556283	2.777900e-33
PRCP	32.556283	2.777900e-33
EGFL7	32.556283	2.777900e-33
IGFBP4	32.556283	2.777900e-33
LMO2	32.555892	2.780403e-33
...	...	...
CDH3	22.903330	1.249310e-23
PDPN	24.988702	1.026356e-25
DSG2	26.957609	1.102531e-27
TPM1	27.349125	4.475840e-28
APOE	30.478444	3.323195e-31

3194 rows × 2 columns

Code

results_table_py = run_ora_catchErrors(mat=rank.T, net=curated, source='geneset', target='genesymbol', verbose=False, n_up=len(rank), n_bottom=0)
len(results_table_py)

766

Code

intTable(results_table_py, folder = folder, fileName = 'Reactome_down.xlsx', save = True)

Code

if len(results_table_py) > 0:
    results_table_py = getAnnGenes(results_table_py, GO2gene['reactome_pathways'], rank_copy)
    _, df = plotGenesInTerm(results = results_table_py, GO2gene = GO2gene['reactome_pathways'], DEGs = rank_copy, n_top_terms = 10, cmap = cmap_down)

Code

if len(results_table_py) > 0:
    intTable(df, folder = folder, fileName = 'genesInTerm_Reactome_down.xlsx', save = True)

4.2.0.2 KEGG

Code

curated = msigdb[msigdb['collection'].isin(['kegg_pathways'])]
curated = curated[~curated.duplicated(['geneset', 'genesymbol'])]

aggregated = curated[["geneset", "genesymbol"]].groupby("geneset").count().rename(columns={"genesymbol": "gene_count"})
curated = curated[~curated.geneset.isin(aggregated[aggregated.gene_count > 200].index.tolist())].copy()
curated = curated[~curated.geneset.isin(aggregated[aggregated.gene_count < 15].index.tolist())].copy()

Code

results_table_py = run_ora_catchErrors(mat=rank.T, net=curated, source='geneset', target='genesymbol', verbose=False, n_up=len(rank), n_bottom=0)

Code

intTable(results_table_py, folder = folder, fileName = 'KEGG_down.xlsx', save = True)

Code

if len(results_table_py) > 0:
    results_table_py = getAnnGenes(results_table_py, GO2gene['kegg_pathways'], rank_copy)
    _, df = plotGenesInTerm(results_table_py, GO2gene['kegg_pathways'], rank_copy, n_top_terms = 10, n_top_genes = 15, cmap = cmap_down)

Code

if len(results_table_py) > 0:
    intTable(df, folder = folder, fileName = 'genesInTerm_KEGG_down.xlsx', save = True)

4.3 All significant

Code

%%R -i allSelected -i allGenes

allGenes_v <- c(allUpSelected)
#print(allGenes_v)
names(allGenes_v) <- allGenes
allGenes_v <- unlist(allGenes_v)

geneNames <- c(allGenes)

ann_org_BP <- topGO::annFUN.org(whichOnto='BP', feasibleGenes=names(allGenes_v), 
                           mapping='org.Hs.eg', ID='symbol')

ann_org_MF <- topGO::annFUN.org(whichOnto='MF', feasibleGenes=names(allGenes_v), 
                           mapping='org.Hs.eg', ID='symbol')

ann_org_CC <- topGO::annFUN.org(whichOnto='CC', feasibleGenes=names(allGenes_v), 
                           mapping='org.Hs.eg', ID='symbol')

selection <- function(allScores){return (as.logical(allScores))}

Biological Process

Code

%%R
#print(lapply(ann_org_BP, count_genes))

GOdata <- new("topGOdata",
  ontology="BP",
  allGenes=allGenes_v,
  annot=annFUN.GO2genes,
  GO2genes=ann_org_BP,
  geneSel = selection,
  nodeSize=10)

Code

%%R -o results

results <- runTest(GOdata, algorithm="weight01",statistic="fisher")

Code

scores = ro.r.score(results)
score_names = ro.r(
'''
names(results@score)
'''
)
go_data = ro.r.GOdata

genesData = ro.r(
'''
geneData(results)
'''
)
genesData

array([13071,   952,    10,  5409], dtype=int32)

Code

#num_summarize = min(100, len(score_names))
results_table = ro.r.GenTable(go_data, weight=results,
        orderBy="weight", topNodes=len(scores))

Code

results_table_py = ro.conversion.rpy2py(results_table)

Code

scores_py = ro.conversion.rpy2py(scores)
score_names = [i for i in score_names]

Code

scores_df = pd.DataFrame({'Scores': scores_py, 'GO.ID': score_names})
results_table_py = results_table_py.merge(scores_df, left_on = 'GO.ID', right_on = 'GO.ID')
results_table_py

	GO.ID	Term	Annotated	Significant	Expected	weight	Scores
0	GO:0001570	vasculogenesis	74	29	5.39	5.4e-12	5.427433e-12
1	GO:0001525	angiogenesis	450	123	32.77	1.2e-11	1.180013e-11
2	GO:0003180	aortic valve morphogenesis	29	16	2.11	1.5e-11	1.527048e-11
3	GO:0016525	negative regulation of angiogenesis	81	25	5.90	5.1e-11	5.130094e-11
4	GO:0030335	positive regulation of cell migration	447	98	32.56	7.3e-11	7.339487e-11
...	...	...	...	...	...	...	...
6269	GO:2000757	negative regulation of peptidyl-lysine a...	20	0	1.46	1.00000	1.000000e+00
6270	GO:2000767	positive regulation of cytoplasmic trans...	13	0	0.95	1.00000	1.000000e+00
6271	GO:2001034	positive regulation of double-strand bre...	15	0	1.09	1.00000	1.000000e+00
6272	GO:2001169	regulation of ATP biosynthetic process	16	0	1.17	1.00000	1.000000e+00
6273	GO:2001244	positive regulation of intrinsic apoptot...	45	0	3.28	1.00000	1.000000e+00

6274 rows × 7 columns

Code

results_table_py = results_table_py[results_table_py['Scores'] < 0.05]
results_table_py = results_table_py[results_table_py['Annotated'] < 200]
results_table_py = results_table_py[results_table_py['Annotated'] > 15]

Code

results_table_py['-log10(pvalue)'] = - np.log10(results_table_py.Scores)
results_table_py['Significant/Annotated'] = results_table_py['Significant'] / results_table_py['Annotated']

Code

intTable(results_table_py, folder = folder, fileName = 'GO_BP_all.xlsx', save = True)

Code

%%R
Res <- GenTable(GOdata, weight=results,
        orderBy="weight", topNodes=length(score(results)))
#print(Res[0:10,])
colnames(Res) <- c("GO.ID", "Term", "Annotated", "Significant", "Expected", "Statistics")
Res$ER <- Res$Significant / Res$Expected
bubbleplot(Res, Ont = 'BP', fillCol = 'forestgreen')

Code

%%R -i markers
plotGenesInTerm_v1(Res, GOdata, SE = markers, nterms=15, ngenes=12,
                             fillCol='forestgreen', log = TRUE)

Code

%%R -i markers -i folder
saveGenesInTerm(Res, GOdata, nterms = 20, path = paste0(folder,'GO_BP_genesInTerm_all.xlsx'), SE = markers)

Molecular Function

Code

%%R

GOdata <- new("topGOdata",
  ontology="MF",
  allGenes=allGenes_v,
  annot=annFUN.GO2genes,
  GO2genes=ann_org_MF,
  geneSel = selection,
  nodeSize=10)

Code

%%R -o results

results <- runTest(GOdata, algorithm="weight01",statistic="fisher")

Code

scores = ro.r.score(results)
score_names = ro.r(
'''
names(results@score)
'''
)
go_data = ro.r.GOdata

genesData = ro.r(
'''
geneData(results)
'''
)
genesData

array([13424,   971,    10,   871], dtype=int32)

Code

#num_summarize = min(100, len(score_names))
results_table = ro.r.GenTable(go_data, weight=results,
        orderBy="weight", topNodes=len(scores))

Code

results_table_py = ro.conversion.rpy2py(results_table)

Code

scores_py = ro.conversion.rpy2py(scores)
score_names = [i for i in score_names]

Code

scores_df = pd.DataFrame({'Scores': scores_py, 'GO.ID': score_names})
results_table_py = results_table_py.merge(scores_df, left_on = 'GO.ID', right_on = 'GO.ID')
results_table_py = results_table_py[results_table_py['Scores'] < 0.05]
results_table_py = results_table_py[results_table_py['Annotated'] < 200]
results_table_py = results_table_py[results_table_py['Annotated'] > 15]

intTable(results_table_py, folder = folder, fileName = 'GO_MF_all.xlsx', save = True)

Code

%%R
Res <- GenTable(GOdata, weight=results,
        orderBy="weight", topNodes=length(score(results)))
#print(Res[0:10,])
colnames(Res) <- c("GO.ID", "Term", "Annotated", "Significant", "Expected", "Statistics")
Res$ER <- Res$Significant / Res$Expected
bubbleplot(Res, Ont = 'MF', fillCol = 'forestgreen')

Code

%%R -i markers
plotGenesInTerm_v1(Res, GOdata, SE = markers, nterms=15, ngenes=12,
                             fillCol='forestgreen', log = TRUE)

Code

%%R -i markers -i folder
saveGenesInTerm(Res, GOdata, nterms = 20, path = paste0(folder,'GO_MF_genesInTerm_all.xlsx'), SE = markers)

Cellular Compartment

Code

%%R

GOdata <- new("topGOdata",
  ontology="CC",
  allGenes=allGenes_v,
  annot=annFUN.GO2genes,
  GO2genes=ann_org_CC,
  geneSel = selection,
  nodeSize=10)

Code

%%R -o results

results <- runTest(GOdata, algorithm="weight01",statistic="fisher")

Code

scores = ro.r.score(results)
score_names = ro.r(
'''
names(results@score)
'''
)
go_data = ro.r.GOdata

genesData = ro.r(
'''
geneData(results)
'''
)
genesData

array([13666,   990,    10,   590], dtype=int32)

Code

#num_summarize = min(100, len(score_names))
results_table = ro.r.GenTable(go_data, weight=results,
        orderBy="weight", topNodes=len(scores))

Code

results_table_py = ro.conversion.rpy2py(results_table)

Code

scores_py = ro.conversion.rpy2py(scores)
score_names = [i for i in score_names]

Code

scores_df = pd.DataFrame({'Scores': scores_py, 'GO.ID': score_names})
results_table_py = results_table_py.merge(scores_df, left_on = 'GO.ID', right_on = 'GO.ID')

Code

results_table_py = results_table_py[results_table_py['Scores'] < 0.05]
results_table_py = results_table_py[results_table_py['Annotated'] < 200]
results_table_py = results_table_py[results_table_py['Annotated'] > 15]

intTable(results_table_py, folder = folder, fileName = 'GO_CC_all.xlsx', save = True)

Code

%%R
Res <- GenTable(GOdata, weight=results,
        orderBy="weight", topNodes=length(score(results)))
#print(Res[0:10,])
colnames(Res) <- c("GO.ID", "Term", "Annotated", "Significant", "Expected", "Statistics")
Res$ER <- Res$Significant / Res$Expected
bubbleplot(Res, Ont = 'CC', fillCol = 'forestgreen')

Code

%%R -i markers
plotGenesInTerm_v1(Res, GOdata, SE = markers, nterms=12, ngenes=12,
                             fillCol='forestgreen', log = TRUE)

Code

%%R -i markers -i folder
saveGenesInTerm(Res, GOdata, nterms = 20, path = paste0(folder,'GO_CC_genesInTerm_all.xlsx'), SE = markers)

Pathway annotation

4.3.0.1 Reactome

Code

curated = msigdb[msigdb['collection'].isin(['reactome_pathways'])]
curated = curated[~curated.duplicated(['geneset', 'genesymbol'])]

aggregated = curated[["geneset", "genesymbol"]].groupby("geneset").count().rename(columns={"genesymbol": "gene_count"})
curated = curated[~curated.geneset.isin(aggregated[aggregated.gene_count > 200].index.tolist())].copy()
curated = curated[~curated.geneset.isin(aggregated[aggregated.gene_count < 15].index.tolist())].copy()

Code

rank = pd.DataFrame(markers['-log10(FDR)'])

rank_copy = rank.copy()
rank_copy['pval'] = markers.loc[rank.index].FDR

Code

rank_copy

	-log10(FDR)	pval
names
PLVAP	32.556283	2.777900e-33
PRCP	32.556283	2.777900e-33
EGFL7	32.556283	2.777900e-33
IGFBP4	32.556283	2.777900e-33
LMO2	32.555892	2.780403e-33
...	...	...
CDH3	22.903330	1.249310e-23
PDPN	24.988702	1.026356e-25
DSG2	26.957609	1.102531e-27
TPM1	27.349125	4.475840e-28
APOE	30.478444	3.323195e-31

3194 rows × 2 columns

Code

results_table_py = run_ora_catchErrors(mat=rank.T, net=curated, source='geneset', target='genesymbol', verbose=False, n_up=len(rank), n_bottom=0)
len(results_table_py)

766

Code

intTable(results_table_py, folder = folder, fileName = 'Reactome_all.xlsx', save = True)

Code

if len(results_table_py) > 0:
    results_table_py = getAnnGenes(results_table_py, GO2gene['reactome_pathways'], rank_copy)
    _, df = plotGenesInTerm(results = results_table_py, GO2gene = GO2gene['reactome_pathways'], DEGs = rank_copy, n_top_terms = 10, cmap = cmap_all)

Code

if len(results_table_py) > 0:
    intTable(df, folder = folder, fileName = 'genesInTerm_Reactome_all.xlsx', save = True)

4.3.0.2 KEGG

Code

curated = msigdb[msigdb['collection'].isin(['kegg_pathways'])]
curated = curated[~curated.duplicated(['geneset', 'genesymbol'])]

aggregated = curated[["geneset", "genesymbol"]].groupby("geneset").count().rename(columns={"genesymbol": "gene_count"})
curated = curated[~curated.geneset.isin(aggregated[aggregated.gene_count > 200].index.tolist())].copy()
curated = curated[~curated.geneset.isin(aggregated[aggregated.gene_count < 15].index.tolist())].copy()

Code

results_table_py = run_ora_catchErrors(mat=rank.T, net=curated, source='geneset', target='genesymbol', verbose=False, n_up=len(rank), n_bottom=0)

Code

intTable(results_table_py, folder = folder, fileName = 'KEGG_all.xlsx', save = True)

Code

if len(results_table_py) > 0:
    results_table_py = getAnnGenes(results_table_py, GO2gene['kegg_pathways'], rank_copy)
    _, df = plotGenesInTerm(results_table_py, GO2gene['kegg_pathways'], rank_copy, n_top_terms = 10, n_top_genes = 15, cmap = cmap_all)

Code

if len(results_table_py) > 0:
    intTable(df, folder = folder, fileName = 'genesInTerm_KEGG_all.xlsx', save = True)